Accurate estimation of the spatial properties of forest soil is essential for sustainable land management. This research aimed to map key soil properties in temperate forests using hybrid machine learning models. The integration of predictive and geostatistical techniques has gained prominence in soil science, with hybrid approaches enhancing prediction accuracy. Precise soil maps serve as a foundational resource for effective soil management, motivating the development of more accurate and cost-efficient mapping methods. We used hybrid machine-learning techniques that incorporated Euclidean distance (Dis), remote sensing (RS) data, and digital elevation models (DEM) to improve spatial predictions. We hypothesized that integrating Euclidean distance data into predictive models would boost the accuracy of soil property maps. Model performance was evaluated using root-mean-square error (RMSE), coefficient of determination (R²), mean absolute error (MAE), and concordance correlation coefficient (CCC). The hybrid RF+GA+Dis model offered the highest accuracy for predicting soil organic carbon (RMSE = 1.810, R2 = 0.763, MAE = 1.883, CCC = 0.803), with similar improvements observed for soil nitrogen, organic carbon stock, bulk density, calcium carbonate, and soil texture. Hybrid models consistently demonstrated a superior performance over individual machine learning methods such as Random Forest (RF) and Genetic Algorithm (GA). Incorporating ancillary data, especially from DEM and RS, substantially ameliorated prediction accuracy for soil physicochemical properties. Among the tested models, those using a broader range of covariates demonstrated a superior performance, with RF+GA+Dis outperforming RF+Dis. These findings confirm that integrating machine learning with comprehensive spatial data is a cost-effective and reliable approach for generating high-resolution soil maps, facilitating precision land management and informed decision-making. This highlights the value of hybrid modeling and diverse covariates in advancing soil property prediction.
Keywords
, , ,
Citation
Ansari N, Moradi M, Taghizadeh-Mehrjardi R (2026). Application of machine learning models and Euclidean distance to predict soil spatial properties. iForest 19: 186-194. - doi: 10.3832/ifor4758-018
Academic Editor
Lorenzo Mw Rossi
Paper history
Received: Nov 14, 2024
Accepted: Oct 25, 2025
First online: Jun 02, 2026
Publication Date: Jun 30, 2026
Publication Time: 7.33 months
© SISEF - The Italian Society of Silviculture and Forest Ecology 2026
Open Access
This article is distributed under the terms of the Creative Commons Attribution-Non Commercial 4.0 International (https://creativecommons.org/licenses/by-nc/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made.
Breakdown by View Type
(Waiting for server response...)
Article Usage
Total Article Views: 60
(from publication date up to now)
Breakdown by View Type
HTML Page Views: 10
Abstract Page Views: 32
PDF Downloads: 18
Citation/Reference Downloads: 0
XML Downloads: 0
Web Metrics
Days since publication: 1
Overall contacts: 60
Avg. contacts per week: 420.00
Article Citations
Article citations are based on data periodically collected from the Clarivate Web of Science web site
(last update: Mar 2025)
(No citations were found up to date. Please come back later)
Publication Metrics
by Dimensions ©
Articles citing this article
List of the papers citing this article based on CrossRef Cited-by.
(1)
Bangroo SA, Najar GR, Achin E, Truong PN (2020)Application of predictor variables in spatial quantification of soil organic carbon and total nitrogen using regression kriging in the North Kashmir forest Himalayas. Catena 193: 104632.
CrossRef |
Gscholar
(2)
Behmanesh S, Moradi M, Pourrezaei J, Basiri R (2024)Does road construction have beneficial effects on vegetation biodiversity and tree regeneration in arid woodlands? Land Degradation and Development 35 (7): 2508-2517.
CrossRef |
Gscholar
(3)
Behrens T, Schmidt K, Rossel RV, Gries P, Scholten T, MacMillan RA (2018)Spatial modelling with Euclidean distance fields and machine learning. European Journal of Soil Science 69 (5): 757-770.
CrossRef |
Gscholar
(4)
Bouslihim Y, Rochdi A, El Amrani Paaza N (2021)Machine learning approaches for the prediction of soil aggregate stability. Heliyon 7 (3): e06480.
CrossRef |
Gscholar
(5)
Breiman L (2001)Random forests. Machine Learning 45: 5-32.
CrossRef |
Gscholar
(6)
Bremner JM, Mulvaney CS (1982)Nitrogen total. In: “1. Methods of soil analysis. Part 2. Chemical and microbiological properties” (Page JL ed). Agronomy Society of America and Soil Science Society of America, Madison, WI, USA, pp. 595-624.
CrossRef |
Gscholar
(7)
Chatterjee S, Huang J, Hartemink AE (2020)Establishing an empirical model for surface soil moisture retrieval at the U.S. climate reference network using Sentinel-1 backscatter and ancillary data. Remote Sensing 12: 1242.
CrossRef |
Gscholar
(8)
Chen L, Ren C, Li L, Wang Y, Zhang B, Wang Z, Li L (2019)A comparative assessment of geostatistical, machine learning, and hybrid approaches for mapping topsoil organic carbon content. ISPRS International Journal of Geo-Information 8: 174.
CrossRef |
Gscholar
(9)
Cheng XF, Shi XZ, Yu DS, Pan XZ, Wang HJ, Sun WX (2004)Using GIS spatial distribution to predict soil organic carbon in subtropical China. Pedosphere 14: 425-431.
Online |
Gscholar
(10)
Cianfrani C, Buri A, Verrecchia E, Guisan A (2018)Generalizing soil properties in geographic space: approaches used and ways forward. PLoS One 13 (12): e0208823.
CrossRef |
Gscholar
(11)
Cutler DR, Edwards TC, Beard KH, Cutler A, Hess KT, Gibson J, Lawler JJ (2007)Random forests for classification in ecology. Ecology 88 (11): 2783-2792.
CrossRef |
Gscholar
(12)
Dai FQ, Zhou QG, Lv ZQ, Wang XM, Liu GC (2014)Spatial prediction of soil organic matter content integrating artificial neural network and ordinary kriging in Tibetan Plateau. Ecological Indicator 45: 184-194.
CrossRef |
Gscholar
(13)
Davatgar N, Neishabouri M, Sepaskhah A (2012)Delineation of site-specific nutrient management zones for a paddy cultivated area based on soil fertility using fuzzy clustering. Geoderma 173: 111-118.
CrossRef |
Gscholar
(14)
Emadi M, Taghizadeh-Mehrjardi R, Cherati A, Danesh M, Mosavi A, Scholten T (2020)Predicting and mapping of soil organic carbon using machine learning algorithms in Northern Iran. Remote sensing 12 (14): 2234.
CrossRef |
Gscholar
(15)
Filippi P, Cattle SR, Bishop T, Jones EJ, Minasny B (2018)Combining ancillary soil data with VisNIR spectra to improve predictions of organic and inorganic carbon content of soils. MethodsX 5: 551-560.
CrossRef |
Gscholar
(16)
Forogh Nasab M, Moradi M, Moradi G, Taghizade-Mehrjardi R (2020)Topsoil carbon stock and soil physicochemical properties in riparian forests and agricultural lands of southwestern Iran. Eurasian Soil Science 53 (10): 1389-1395.
CrossRef |
Gscholar
(17)
Habashi H (2015)Microbial respiration and microbial biomass C relationship with soil organic matter in different types of mixed beech forest. Forest Research and Development 1 (2): 135-144.
Gscholar
(18)
Hashemi Rad S, Kiani F, Meftah Helghi M, Hematzadeh Y (2018)Effect of land use on physical and chemical parameters of soil and sediment in Qarnave and Yelcheshme watersheds, Golestan Province, Iran. Environmental Resources Research 2: 89-102.
CrossRef |
Gscholar
(19)
Hengl T, Heuvelink GBM, Rossiter DG (2007)About regression-kriging: from equations to case studies. Computers and Geosciences 33: 1301-1315.
CrossRef |
Gscholar
(20)
Holliday VT (1990)Methods of soil analysis, Part 1, physical and mineralogical methods (2nd edn). A. Klute, Ed., 1986, American Society of Agronomy, Agronomy Monographs 9 (1), Madison, Wisconsin, 1188. Geoarchaeology 5 (1): 87-89.
CrossRef |
Gscholar
(21)
John K, Isong IA, Kebonye NM, Ayito EO, Agyeman PC, Afu SM (2020)Using machine learning algorithms to estimate soil organic carbon variability with environmental variables and soil nutrient indicators in an alluvial soil. Land 9: 487.
CrossRef |
Gscholar
(22)
John R, Dalling JW, Harms KE, Yavitt JB, Stallard RF, Mirabello M, Hubbell SP, Valencia R, Navarrete H, Vallejo M, Foster RB (2007)Soil nutrients influence spatial distributions of tropical tree species. Proceedings of the National Academy of Sciences USA 104: 864-869.
CrossRef |
Gscholar
(23)
Kassai P, Kocsis M, Szatmári G, Makó A, Mészáros J, Laborczi A, Magyar Z, Takacs K, Szabó B (2025)Large-scale mapping of soil particle size distribution using legacy data and machine learning-based pedotransfer functions. Geoderma 454: 117178.
CrossRef |
Gscholar
(24)
Kebonye NM, Taghizadeh-Mehrjardi R, John K, Agyeman PC, Kakhani N, Seletlo Z, Motlhetlhi L, Moyo B, Scholten T (2024)Spatial scale drives pedodiversity-elevation relationship in Botswana. Geomatica 76 (2): 100037.
CrossRef |
Gscholar
(25)
Kim HJ, Mawuntu KBA, Park TW, Kim HS, Park JY, Jeong YS (2023)Spatial Autocorrelation Incorporated Machine Learning Model for Geotechnical Subsurface Modeling. Applied Sciences 13 (7): 4497.
CrossRef |
Gscholar
(26)
Klein-Raufhake T, Hölzel N, Schaper JJ, Elmer M, Fornfeist M, Linnemann B, Meyer M, Neuenkamp L, Rentemeister K, Santora L, Jens W, Hamer U (2024)Disentangling the impact of forest management intensity components on soil biological processes. Global Change Biology 31 (1): e70018.
CrossRef |
Gscholar
(27)
Li H, Meng Z, Ren X, Han Y (2025)Variations in the physicochemical properties of soil, enzyme activities, and the characteristics of bacterial communities within algal biocrusts and subsoils across different plant communities. Global Ecology and Conservation 58: e03455.
CrossRef |
Gscholar
(28)
Mansor SB, Pormanafi S, Mahmud ARB, Pirasteh S (2012)Optimization of land use suitability for agriculture using integrated geospatial models and genetic algorithms. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences 2: 234-299.
CrossRef |
Gscholar
(29)
Manteghi S, Moravej K, Mousavi SR, Delavar MA, Mastinu A (2024)Digital soil mapping for soil types using machine learning approaches at the landscape scale in the arid regions of Iran. Advances in Space Research 74 (1): 1-16.
CrossRef |
Gscholar
(30)
Marchetti A, Piccini C, Francaviglia R, Santucci S, Chiuchiarelli I (2008)Evaluation of soil organic matter content in Teramo province, Central Italy. Advances in GeoEcology 39: 345-356.
Online |
Gscholar
(31)
Merwin HD, Peech M (1951)Exchangeability of soil potassium in the sand, silt, and clay fractions as influenced by the nature of the complementary exchangeable cation 1. Soil Science Society of America Journal 15 (C): 125-128.
CrossRef |
Gscholar
(32)
Michalewicz Z, Schoenauer M (1996)Evolutionary algorithms for constrained parameter optimization problems. Evolutionary Computation 4 (1): 1-32.
CrossRef |
Gscholar
(33)
Moradi Behbahani S, Moradi M, Basiri R, Mirzaei J (2017)Sand mining disturbances and their effects on the diversity of arbuscular mycorrhizal fungi in a riparian forest of Iran. Journal of Arid Land 9 (6): 837-849.
CrossRef |
Gscholar
(34)
Moradi M, Imani F, Naji HR, Moradi Behbahani S, Ahmadi MT (2017)Variation in soil carbon stock and nutrient content in sand dunes after afforestation by
Prosopis juliflora in the Khuzestan province (Iran). iForest 10 (3): 585-589.
CrossRef |
Gscholar
(35)
Moradi M, Jorfi MR, Basiri R, Yusef Naanaei S, Heydari M (2022)Beneficial effects of livestock exclusion on tree regeneration, understory plant diversity, and soil properties in semiarid forests in Iran. Land Degradation and Development 33 (2): 324-332.
CrossRef |
Gscholar
(36)
Mousavi A, Shahabzi F, Oustan S, Jafarzadeh A, Minasny B (2020)Application of two data mining techniques for mapping the spatial distribution of soil organic carbon (case study: east shore of Urmia Lake). Water and Soil 34 (3): 689-705.
CrossRef |
Gscholar
(37)
Nabiollahi K, Eskandari Sh Taghizadeh-Mehrjardi R, Kerry R, Triantafilis J (2019)Assessing soil organic carbon stocks under land-use change scenarios using random forest models. Carbon Management 10 (1): 63-77.
CrossRef |
Gscholar
(38)
Ogunwole JO, Obidike EO, Timm LC, Odunze AC, Gabriels DM (2014)Assessment of spatial distribution of selected soil properties geospatial statistical tools. Communications in Soil Science and Plant Analysis 45 (16): 2182-2200.
CrossRef |
Gscholar
(39)
Olsen SR, Cole CV, Watanabe FS, Dean LA (1954)Estimation of available phosphorus in soils by extraction with sodium bicarbonate. USDA, Washington, DC, USA, pp. 1-19.
Online |
Gscholar
(40)
Padarian J, Minasny B, Mcbratney AB (2020)Machine learning and soil sciences: a review aided by machine learning tools. Soil 6: 35-52.
CrossRef |
Gscholar
(41)
Page-Dumroese DS, Brown RE, Jurgensen MF, Mroz GD (1999)Comparison of methods for determining bulk densities of Rocky Forest soils. Soil Science Society of America Journal 63 (2): 379.
CrossRef |
Gscholar
(42)
Pandey M, Mishra A, Swamy SL, Anderson JT, Thakur TK (2025)Machine learning-based monitoring of land cover and reclamation plantations on coal-mined landscape using Sentinel 2 data. Environmental and Sustainability Indicators 25 (25): 100585.
CrossRef |
Gscholar
(43)
Parajuli M, Cristan R, Daniel MJ, Rijal A, Mitchell D, McDonald T, Gallagher T (2025)Integrating high-resolution imagery, deep learning, and GIS to estimate soil erosion following timber harvesting. Remote Sensing Applications: Society and Environment 37 (37): 101498.
CrossRef |
Gscholar
(44)
Parvizi Y, Fatehi S (2025)Geospatial digital mapping of soil organic carbon using machine learning and geostatistical methods in different land uses. Scientific Report 15: 4449.
CrossRef |
Gscholar
(45)
Piccini C, Francaviglia R, Marchetti A (2020)Predicted maps for soil organic matter evaluation: the case of Abruzzo Region (Italy). Land 9: 349.
CrossRef |
Gscholar
(46)
Sagheb Talebi K, Sajedi T, Pourhashemi M (2013)Forests of Iran. Plant and vegetation. Springer Nature, Netherlands, pp. 152.
CrossRef |
Gscholar
(47)
Sefidi K, Mohadjer MRM (2010)Characteristics of coarse woody debris in successional stages of natural beech (
Fagus orientalis) forests of Northern Iran. Journal of Forest Science 56 (1): 7-17.
CrossRef |
Gscholar
(48)
Setälä HM, Francini G, Allen JA, Hui N, Jumpponen A, Kotze DJ (2016)Vegetation type and age drive changes in soil properties, nitrogen, and carbon sequestration in urban parks under cold climate. Frontiers in Ecology and Evolution 4: 93.
CrossRef |
Gscholar
(49)
Song YQ, Yang LA, Li B, Hu YM, Wang AL, Zhou W, Cui XS, Liu YL (2017)Spatial prediction of soil organic matter using a hybrid geostatistical model of an extreme learning machine and ordinary kriging. Sustainability 9 (5): 754.
CrossRef |
Gscholar
(50)
Sun W, Zhang X, Zou B, Wu T (2017)Exploring the potential of spectral classification in estimation of soil contaminant elements. Remote Sensing 9 (6): 632.
CrossRef |
Gscholar
(51)
Szabó B, Szatmári G, Takács K, Laborczi A, Makó A, Rajkai K, Pásztor L (2019)Mapping soil hydraulic properties using random-forest-based pedotransfer functions and geostatistics. Hydrology and Earth System Sciences 23 (6): 2615-2635.
CrossRef |
Gscholar
(52)
Tziachris P, Aschonitis V, Chatzistathis T, Papadopoulou M (2019)Assessment of spatial hybrid methods for predicting soil organic matter using DEM derivatives and soil parameters. Catena 174: 206-216.
CrossRef |
Gscholar
(53)
Veen GF, Fry EL, Hooven FC, Kardol P, Morriën E, De Long JR (2019)The role of plant litter in driving plant-soil feedbacks. Frontiers in Environmental Science 7: 168.
CrossRef |
Gscholar
(54)
Wadoux A, Minasny B, McBratney AB (2020)Machine learning for digital soil mapping: applications, challenges and suggested solutions. Earth Science Reviews 210: 103359.
CrossRef |
Gscholar
(55)
Walkley A, Black IA (1951)An examination of the Degtjareff method for determining organic carbon in soils: effect of variations in digestion conditions and of inorganic soil constituents. Soil Science 63: 251-263.
CrossRef |
Gscholar
(56)
Wan JZ, Yu JH, Yin GJ, Song ZM, Wei DX, Wang CJ (2019)Effects of soil properties on the spatial distribution of forest vegetation across China. Global Ecology and Conservation 18: e00635.
CrossRef |
Gscholar
(57)
Wang N, Chen S, Huang J, Frappart F, Taghizadeh R, Zhang X, Wigneron JP, Xue J, Xiao Y, Peng J, Shi Z (2024)Global soil salinity estimation at 10 m using multi-source remote sensing. Journal of Remote Sensing 4: 130.
CrossRef |
Gscholar
(58)
Xie X, Zheng Y, Li Y (2015)Genetic Algorithm and its performance analysis for scheduling a single crane. Discrete Dynamics in Nature and Society 2015: 18436.
CrossRef |
Gscholar
(59)
Yang H, Miao N, Li S, Ma R, Liao Z, Wang W, Sun H (2019)Relationship between stand characteristics and soil properties of two typical forest plantations in the mountainous area of Western Sichuan, China. Journal of Mountain Science 16 (8): 1816-1832.
CrossRef |
Gscholar
(60)
Zeraatpisheh M, Ayoubi S, Jafari A, Tajik S, Finke P (2019)Digital mapping of soil properties using multiple machine learning in a semi-arid region, central Iran. Geoderma 338: 445-452.
CrossRef |
Gscholar
(61)
Zolfaghari Nia M, Moradi M, Moradi G, Taghizadeh-Mehrjardi R (2023)Machine learning models for prediction of soil properties in the riparian forests. Land 12 (1): 32.
CrossRef |
Gscholar
